Triple
T3473092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | QLED televisions |
E73308
|
entity |
| Predicate | usesBacklight |
P33708
|
FINISHED |
| Object | LED backlight |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: LED backlight | Statement: [QLED televisions, usesBacklight, LED backlight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBacklight Context triple: [QLED televisions, usesBacklight, LED backlight]
-
A.
usesBacklightTechnology
chosen
Indicates that one entity employs backlight technology to illuminate or enhance the visibility of another entity or its display.
-
B.
hasBacklitKeyboard
Indicates that an entity is equipped with a keyboard that includes built-in lighting behind the keys.
-
C.
hasBackupBattery
Indicates that an entity is equipped with an additional battery intended to provide power when the primary power source is unavailable or fails.
-
D.
hasOnboardLEDs
Indicates that one entity is equipped with built-in LED lights as part of its hardware.
-
E.
hasAlwaysOnDisplay
Indicates that an entity features an always-on display capability that remains visible without fully waking the device.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85b2fed48190948c8765e453d270 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb3e03e081908aa09291bbf351bd |
completed | March 8, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69adae07802c8190919c49b0e65b2797 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:17 p.m.